Cancer Res Treat.  2021 Jul;53(3):773-783. 10.4143/crt.2020.974.

LASSO-Based Machine Learning Algorithm for Prediction of Lymph Node Metastasis in T1 Colorectal Cancer

Affiliations
  • 1Department of Surgery, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul, Korea
  • 2Department of Pathology, Yongin Severance Hospital, Yonsei University College of Medicine, Seoul, Korea
  • 3Department of Surgery, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea
  • 4Biostatistics Collaboration Unit, Yonsei University College of Medicine, Seoul, Korea
  • 5Department of Pathology, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea

Abstract

Purpose
The role of tumor-infiltrating lymphocytes (TILs) in predicting lymph node metastasis (LNM) in patients with T1 colorectal cancer (CRC) remains unclear. Furthermore, clinical utility of a machine learning–based approach has not been widely studied.
Materials and Methods
Immunohistochemistry for TILs against CD3, CD8, and forkhead box P3 in both center and invasive margin of the tumor were performed using surgically resected T1 CRC slides. Three hundred and sixteen patients were enrolled and categorized into training (n=221) and validation (n=95) sets via random sampling. Using clinicopathologic variables including TILs, the least absolute shrinkage and selection operator (LASSO) regression model was applied for variable selection and predictive signature building in the training set. The predictive accuracy of our model and the Japanese criteria were compared using area under the receiver operating characteristic (AUROC), net reclassification improvement (NRI)/integrated discrimination improvement (IDI), and decision curve analysis (DCA) in the validation set.
Results
LNM was detected in 29 (13.1%) and 12 (12.6%) patients in training and validation sets, respectively. Nine variables were selected and used to generate the LASSO model. Its performance was similar in training and validation sets (AUROC, 0.795 vs. 0.765; p=0.747). In the validation set, the LASSO model showed better outcomes in predicting LNM than Japanese criteria, as measured by AUROC (0.765 vs. 0.518, p=0.003) and NRI (0.447, p=0.039)/IDI (0.121, p=0.034). DCA showed positive net benefits in using our model.
Conclusion
Our LASSO model incorporating histopathologic parameters and TILs showed superior performance compared to conventional Japanese criteria in predicting LNM in patients with T1 CRC.

Keyword

Tumor-infiltrating lymphocytes; Lymph node; T1 colorectal cancer; Machine learning; LASSO

Figure

  • Fig. 1 Selection of significant parameters in clinicopathologic variables in the training set and definition of linear predictor. (A) Ten time cross-validation for tuning parameter selection in the LASSO model. (B) LASSO coefficient profiles. The LASSO was used for regression of high dimensional predictors. The method uses an L1 penalty to shrink some regression coefficients to exactly zero. The binomial deviance curve was plotted versus log (λ), where λ is the tuning parameter (A). LASSO coefficient profiles of clinicopathologic variables (B). LASSO, least absolute shrinkage and selection operator.

  • Fig. 2 Comparison of AUROC between LASSO model in the training and validation sets and Japanese criteria in the validation set. AUC, area under the curve; AUROC, area under the receiver operating characteristic; CI, confidence interval; LASSO, least absolute shrinkage and selection operator.

  • Fig. 3 Decision curve analysis of Japanese criteria and LASSO model in the training (A) and validation (B) set. The y-axis measures the net benefit. The green line represents the LASSO model. The red line represents the Japanese criteria. The gray line represents the assumption that all patients underwent surgeries. The black line represents the assumption that patients underwent no surgeries. The net benefit was calculated by subtracting the proportion of all patients who are false positive from the proportion who are true positive, weighting by the relative harm of forgoing treatment compared with the negative consequences of an unnecessary treatment. The decision curve showed that if the threshold probability of a patient or doctor is >10%, using the LASSO model in the current study to predict LNM adds more benefit than the treat-all-patients scheme or the treat-none scheme. For example, if the personal threshold probability of a patient is 20% (i.e., the patient would opt for surgery if his/her probability of LNM was > 20%), then the net benefit is 0.35 when using the LASSO model to make the decision of whether to undergo surgery, with added benefit than the treat-all scheme or the treat-none scheme. This decision curve analysis showed that the net benefit was comparable on the basis of the Japanese criteria and the treat-all or treat-none strategies. LASSO, least absolute shrinkage and selection operator; LNM, lymph node metastasis.


Reference

References

1. Dai W, Mo S, Xiang W, Han L, Li Q, Wang R, et al. The critical role of tumor size in predicting prognosis for T1 colon cancer. Oncologist. 2020; 25:244–51.
Article
2. Gunderson LL, Jessup JM, Sargent DJ, Greene FL, Stewart AK. Revised TN categorization for colon cancer based on national survival outcomes data. J Clin Oncol. 2010; 28:264–71.
Article
3. Hashiguchi Y, Muro K, Saito Y, Ito Y, Ajioka Y, Hamaguchi T, et al. Japanese Society for Cancer of the Colon and Rectum (JSCCR) guidelines 2019 for the treatment of colorectal cancer. Int J Clin Oncol. 2020; 25:1–42.
Article
4. Kitajima K, Fujimori T, Fujii S, Takeda J, Ohkura Y, Kawamata H, et al. Correlations between lymph node metastasis and depth of submucosal invasion in submucosal invasive colorectal carcinoma: a Japanese collaborative study. J Gastroenterol. 2004; 39:534–43.
Article
5. Kobayashi H, Mochizuki H, Morita T, Kotake K, Teramoto T, Kameoka S, et al. Characteristics of recurrence after curative resection for T1 colorectal cancer: Japanese multicenter study. J Gastroenterol. 2011; 46:203–11.
Article
6. Oh JR, Park B, Lee S, Han KS, Youk EG, Lee DH, et al. Nomogram development and external validation for predicting the risk of lymph node metastasis in T1 colorectal cancer. Cancer Res Treat. 2019; 51:1275–84.
Article
7. Ueno H, Mochizuki H, Hashiguchi Y, Shimazaki H, Aida S, Hase K, et al. Risk factors for an adverse outcome in early invasive colorectal carcinoma. Gastroenterology. 2004; 127:385–94.
Article
8. Nishida T, Egashira Y, Akutagawa H, Fujii M, Uchiyama K, Shibayama Y, et al. Predictors of lymph node metastasis in T1 colorectal carcinoma: an immunophenotypic analysis of 265 patients. Dis Colon Rectum. 2014; 57:905–15.
9. Jung CK, Jung SH, Yim SH, Jung JH, Choi HJ, Kang WK, et al. Predictive microRNAs for lymph node metastasis in endoscopically resectable submucosal colorectal cancer. Oncotarget. 2016; 7:32902–15.
Article
10. Geng Y, Shao Y, He W, Hu W, Xu Y, Chen J, et al. Prognostic role of tumor-infiltrating lymphocytes in lung cancer: a meta-analysis. Cell Physiol Biochem. 2015; 37:1560–71.
Article
11. Cha YJ, Park EJ, Baik SH, Lee KY, Kang J. Clinical significance of tumor-infiltrating lymphocytes and neutrophil-to-lymphocyte ratio in patients with stage III colon cancer who underwent surgery followed by FOLFOX chemotherapy. Sci Rep. 2019; 9:11617.
Article
12. Yu P, Fu YX. Tumor-infiltrating T lymphocytes: friends or foes? Lab Invest. 2006; 86:231–45.
Article
13. Hori S, Nomura T, Sakaguchi S. Control of regulatory T cell development by the transcription factor Foxp3. Science. 2003; 299:1057–61.
14. deLeeuw RJ, Kost SE, Kakal JA, Nelson BH. The prognostic value of FoxP3+ tumor-infiltrating lymphocytes in cancer: a critical review of the literature. Clin Cancer Res. 2012; 18:3022–9.
Article
15. Pages F, Mlecnik B, Marliot F, Bindea G, Ou FS, Bifulco C, et al. International validation of the consensus Immunoscore for the classification of colon cancer: a prognostic and accuracy study. Lancet. 2018; 391:2128–39.
16. Cavalleri T, Bianchi P, Basso G, Celesti G, Grizzi F, Bossi P, et al. Combined low densities of FoxP3(+) and CD3(+) tumor-infiltrating lymphocytes identify stage II colorectal cancer at high risk of progression. Cancer Immunol Res. 2019; 7:751–8.
Article
17. Reichling C, Taieb J, Derangere V, Klopfenstein Q, Le Malicot K, Gornet JM, et al. Artificial intelligence-guided tissue analysis combined with immune infiltrate assessment predicts stage III colon cancer outcomes in PETACC08 study. Gut. 2020; 69:681–90.
Article
18. Ichimasa K, Kudo SE, Mori Y, Misawa M, Matsudaira S, Kouyama Y, et al. Artificial intelligence may help in predicting the need for additional surgery after endoscopic resection of T1 colorectal cancer. Endoscopy. 2018; 50:230–40.
Article
19. Huang YQ, Liang CH, He L, Tian J, Liang CS, Chen X, et al. Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol. 2016; 34:2157–64.
Article
20. Akishima-Fukasawa Y, Ishikawa Y, Akasaka Y, Uzuki M, Inomata N, Yokoo T, et al. Histopathological predictors of regional lymph node metastasis at the invasive front in early colorectal cancer. Histopathology. 2011; 59:470–81.
Article
21. Watanabe T, Itabashi M, Shimada Y, Tanaka S, Ito Y, Ajioka Y, et al. Japanese Society for Cancer of the Colon and Rectum (JSCCR) guidelines 2010 for the treatment of colorectal cancer. Int J Clin Oncol. 2012; 17:1–29.
Article
22. Wada H, Shiozawa M, Katayama K, Okamoto N, Miyagi Y, Rino Y, et al. Systematic review and meta-analysis of histopathological predictive factors for lymph node metastasis in T1 colorectal cancer. J Gastroenterol. 2015; 50:727–34.
Article
23. Zhao Y, Ge X, He J, Cheng Y, Wang Z, Wang J, et al. The prognostic value of tumor-infiltrating lymphocytes in colorectal cancer differs by anatomical subsite: a systematic review and meta-analysis. World J Surg Oncol. 2019; 17:85.
Article
24. Takamatsu M, Yamamoto N, Kawachi H, Chino A, Saito S, Ueno M, et al. Prediction of early colorectal cancer metastasis by machine learning using digital slide images. Comput Methods Programs Biomed. 2019; 178:155–61.
Article
25. Backes Y, Elias SG, Groen JN, Schwartz MP, Wolfhagen FH, Geesing JM, et al. Histologic factors associated with need for surgery in patients with pedunculated T1 colorectal carcinomas. Gastroenterology. 2018; 154:1647–59.
Article
26. Kudo S. Endoscopic mucosal resection of flat and depressed types of early colorectal cancer. Endoscopy. 1993; 25:455–61.
Article
27. Kikuchi R, Takano M, Takagi K, Fujimoto N, Nozaki R, Fujiyoshi T, et al. Management of early invasive colorectal cancer: risk of recurrence and clinical guidelines. Dis Colon Rectum. 1995; 38:1286–95.
28. Nascimbeni R, Burgart LJ, Nivatvongs S, Larson DR. Risk of lymph node metastasis in T1 carcinoma of the colon and rectum. Dis Colon Rectum. 2002; 45:200–6.
Article
29. Choi DH, Sohn DK, Chang HJ, Lim SB, Choi HS, Jeong SY. Indications for subsequent surgery after endoscopic resection of submucosally invasive colorectal carcinomas: a prospective cohort study. Dis Colon Rectum. 2009; 52:438–45.
30. Klauschen F, Muller KR, Binder A, Bockmayr M, Hagele M, Seegerer P, et al. Scoring of tumor-infiltrating lymphocytes: from visual estimation to machine learning. Semin Cancer Biol. 2018; 52:151–7.
Article
Full Text Links
  • CRT
Actions
Cited
CITED
export Copy
Close
Share
  • Twitter
  • Facebook
Similar articles
Copyright © 2024 by Korean Association of Medical Journal Editors. All rights reserved.     E-mail: koreamed@kamje.or.kr